Note: This project is heavily under development and any feedback is greatly appreciated.

This repository consists of several packages, each residing in its own directory under the packages/ directory:

• Anthropic Adapter: The adapter for the Anthropic API client. More Info
• Chat: Chat functionalities for Modelflow AI. More Info
• Completion: Completion functionalities for Modelflow AI. More Info
• Decision Tree: A decision tree represents a series of decisions and the possible outcome of those decisions. More Info
• Elasticsearch Embeddings Store: This package stores embeddings in Elasticsearch. More Info
• Embeddings: Handles the embeddings for the AI models. More Info
• Experts: It provides a set of tools for so called experts comparable to OpenAI GPTs or OpenGPTs. More Info
• Fireworks.ai Adapter: The adapter for integrating LLMs by fireworks.ai. More Info
• Image: Handles image requests like generation or edits. More Info
• Mistral Adapter: The adapter for the Mistral API client. More Info
• Ollama Adapter: The adapter for the Ollama API client. More Info
• OpenAI Adapter: The adapter for integrating OpenAI models. More Info
• Prompt Template: Provides templates for AI prompts. More Info
• Qdrant Embeddings Store: This package stores embeddings in Qdrant. More Info
• Tools: Contains tools to extend models in a Modelflow AI Request. More Info

Independent packages:

• Anthropic: A comprehensive API client for Anthropic AI. More Info
• Api-Client: A basic API client. More Info
• Mistral: A comprehensive API client for Mistral AI. More Info
• Ollama: A comprehensive API client for Ollama. More Info

Modelflow AI integrates with the following php frameworks:

• Symfony More Info

To install Modelflow AI, you need to have PHP 8.2 or higher and Composer installed on your machine. Then, you can clone this repository and run composer install in the root directory.

Each package has its own usage instructions. Please refer to the README file in each package's directory for specific usage instructions.

Contributions are welcome. Please open an issue to discuss your idea or submit a pull request.

This project is licensed under the MIT License. For the full copyright and license information, please view the LICENSE file that was distributed with this source code.